Image region entropy: A measure of "visualness" of web images associated with one concept

Keiji Yanai, Kobus Barnard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

56 Scopus citations

Abstract

We propose a new method to measure "visualness" of concepts, that is, what extent concepts have visual characteristics. To know which concept has visually discriminative power is important for image annotation, especially automatic image annotation by image recognition system, since not all concepts are related to visual contents. Our method performs probabilistic region selection for images which are labeled as concept "X" or "non-X", and computes an entropy measure which represents "visualness" of concepts. In the experiments, we collected about forty thousand images from the World-Wide Web using the Google Image Search for 150 concepts. We examined which concepts are suitable for annotation of image contents.

Original languageEnglish (US)
Title of host publicationProceedings of the 13th ACM International Conference on Multimedia, MM 2005
Pages419-422
Number of pages4
DOIs
StatePublished - Dec 1 2005
Event13th ACM International Conference on Multimedia, MM 2005 - Singapore, Singapore
Duration: Nov 6 2005Nov 11 2005

Publication series

NameProceedings of the 13th ACM International Conference on Multimedia, MM 2005

Other

Other13th ACM International Conference on Multimedia, MM 2005
CountrySingapore
CitySingapore
Period11/6/0511/11/05

Keywords

  • Image annotation
  • Probabilistic image selection
  • Web image mining

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Software

Fingerprint Dive into the research topics of 'Image region entropy: A measure of "visualness" of web images associated with one concept'. Together they form a unique fingerprint.

  • Cite this

    Yanai, K., & Barnard, K. (2005). Image region entropy: A measure of "visualness" of web images associated with one concept. In Proceedings of the 13th ACM International Conference on Multimedia, MM 2005 (pp. 419-422). (Proceedings of the 13th ACM International Conference on Multimedia, MM 2005). https://doi.org/10.1145/1101149.1101241